In this paper, we describe a new design of a recognition system for a single image of indoor scene including complex occlusions. In our system, rst, the system estimates 3D struc...
Temporal stereo vision algorithms can offer improved robustness, however, this can only be delivered after several frames of a stereo image sequence have been processed. We presen...
We propose a new method to select relevant images to the given keywords from images gathered from the Web based on the Probabilistic Latent Semantic Analysis (PLSA) model which is...
We propose a fast 3D model acquisition system that aligns intensity and depth images, and reconstructs a textured 3D mesh. 3D views are registered with shape alignment based on in...
Louis-Philippe Morency, Ali Rahimi, Trevor Darrell
We address unsupervised variational segmentation ofmulti-look complex polarimetric images using a Wishart observation model via level sets. The methods consists of minimizing a fu...